Stratmillin tutkimusagentin kirjoittamia tiivistelmiä ja keskeisiä ajatuksia kirjoista, tutkimuksista, artikkeleista ja koodista, joita tekoälyagenttimme lukevat. Jokaisella sivulla on linkki alkuperäislähteeseen.
3,481 dokumenttia
This strategy selects Chinese convertible bonds nearing maturity, aiming to combine a price discount to redemption value with screening for issuer credit risk. It excludes bonds linked to special-treatment stocks, requires positive trailing earnings and…
This brief response defines quantitative investing as using tools to extract patterns from historical data. It frames time-series analysis as a way to improve the odds of making a successful decision and cross-sectional analysis as a way to seek better…
The document explains a model-training error caused by a feature stored as an object or string rather than a numeric value. Its diagnostic approach is to inspect the training data and identify which input column has the incompatible type. The example points…
This forum post asks how to migrate several legacy factors from an earlier version of a quantitative research platform into a newer one. The expressions cover an industry-grouped beta adjustment, a rolling correlation between log volume and absolute returns,…
This Chinese research note explores bull-bear indicators in three equity applications: timing broad indices, rotating among industries, and setting index constituent exposure. For direct index timing, it adapts the dual moving average idea by comparing…
This research summary explains how alpha factors can be represented by factor-mimicking portfolios (FMPs) under a stock covariance model, and how linear combinations of factors correspond to combinations of their mimicking portfolios. It frames factor…
The article proposes a discretionary momentum framework for Chinese A-shares. It starts with stocks that have recently hit the daily price limit or shown unusual activity, then recommends tracking them in a watchlist and excluding names without a recent…
This description explains a limit-order market-making strategy based on the Avellaneda–Stoikov framework. It sets a reservation price and optimal bid-ask spread using estimated volatility, order-book liquidity, inventory relative to a target allocation, the…
This research review examines whether stocks moving together always reduce active mutual fund performance. It distinguishes synchronicity driven by broad market information from synchronicity associated with noise trading, proposing that investor sentiment…
This report outlines a short-term reversal strategy for China’s CSI 800 stocks. It combines a moving-average system intended to classify trend state through cycle analysis with multi-timeframe MACD divergence. A bullish divergence occurs when price makes a…
This research report studies portfolio construction around a weekly stock-selection model called AlphaNet, built from price and volume data. It examines several portfolio optimization approaches intended to accommodate different risk and return objectives.…
This research summary proposes a stock illiquidity factor based on the shortest path through intraday candlestick data. It aims to improve on a conventional proxy that relates price returns to trading volume, which the authors say can be unreliable during…
The document explains two settings in a rolling-data module used to prepare features for securities. The window size controls how many consecutive observations are grouped into each sample. Its example uses five sequential values and a window of three to…
This research summary reviews the low-volatility equity factor across overseas markets and mainland Chinese shares. It describes the behavioral explanation that highly volatile stocks may be more vulnerable to speculation and rich valuations, while…
The document outlines a single-asset strategy based on the average of 30-day and 72-day moving averages. It treats a close below 80% of that average as a deeply discounted condition, then waits for a 5% rebound from the triggering close before buying. For an…
This essay describes quantitative trading as the automated execution of investment models designed and assessed by people, rather than as an independent mechanism for discovering profitable strategies. It emphasizes that rule-based systems can apply…
This BigQuant support exchange explains a prediction error associated with missing or infinite values while constructing label bins. It suggests checking whether the target label is absent or contains many missing values. The further diagnosis is that the…
This article explains the theoretical link between beta pricing models, including the Fama-French three-factor model, and stochastic discount factors (SDFs). It distinguishes absolute pricing, which connects asset values to macroeconomic risks, from relative…
This review summarizes research testing whether small-cap stocks continued to outperform large caps across calendar effects in US equities. The underlying study forms portfolios from the smallest and largest size groups and examines the return spread around…
A BigQuant forum answer addresses why a stock selection strategy’s returns changed from positive to negative after neutralizing and standardizing its inputs. The reply explains that StockRanker uses a tree-based structure and, according to the respondent,…
This study examines whether generative adversarial networks can produce realistic multi-asset financial time series. It combines the convolutional architecture of DCGAN with the Wasserstein-distance loss used by WGAN: convolutional layers replace some…
This strategy rotates among a fixed pool of 11 ETFs spanning several asset classes and markets. Every five trading days, it ranks candidates using a 25-day linear-regression slope multiplied by R-squared, then adds a short-term signal based on the five-day…
This report summarizes stock-selection results for several machine-learning models across broad Chinese equity universes and constituent groups tied to the CSI 300, CSI 500, and CSI 800. It compares weekly, recent-month, and 2018-to-date excess returns, and…
This brief forum entry addresses an SQL error encountered while trying to neutralize a rolling turnover measure against total market capitalization. It points readers toward a regression-residual function as an alternative to a direct neutralization call.…